Prediction models for dementia and neuropathology in the oldest old: The Vantaa 85+ cohort study 11 Medical and Health Sciences 1109 Neurosciences

Anette Hall, Timo Pekkala, Tuomo Polvikoski, Mark van Gils, Miia Kivipelto, Jyrki Lötjönen, Jussi Mattila, Mia Kero, Liisa Myllykangas, Mira Mäkelä, Minna Oinas, Anders Paetau, Hilkka Soininen, Maarit Tanskanen, Alina Solomon (Corresponding Author)

Research output: Contribution to journalArticleScientificpeer-review

2 Citations (Scopus)

Abstract

Background: We developed multifactorial models for predicting incident dementia and brain pathology in the oldest old using the Vantaa 85+ cohort. Methods: We included participants without dementia at baseline and at least 2 years of follow-up (N = 245) for dementia prediction or with autopsy data (N = 163) for pathology. A supervised machine learning method was used for model development, considering sociodemographic, cognitive, clinical, vascular, and lifestyle factors, as well as APOE genotype. Neuropathological assessments included β-amyloid, neurofibrillary tangles and neuritic plaques, cerebral amyloid angiopathy (CAA), macro- and microscopic infarcts, α-synuclein pathology, hippocampal sclerosis, and TDP-43. Results: Prediction model performance was evaluated using AUC for 10 × 10-fold cross-validation. Overall AUCs were 0.73 for dementia, 0.64-0.68 for Alzheimer's disease (AD)- or amyloid-related pathologies, 0.72 for macroinfarcts, and 0.61 for microinfarcts. Predictors for dementia were different from those in previous reports of younger populations; for example, age, sex, and vascular and lifestyle factors were not predictive. Predictors for dementia versus pathology were also different, because cognition and education predicted dementia but not AD- or amyloid-related pathologies. APOE genotype was most consistently present across all models. APOE alleles had a different impact: ϵ4 did not predict dementia, but it did predict all AD- or amyloid-related pathologies; ϵ2 predicted dementia, but it was protective against amyloid and neuropathological AD; and ϵ3ϵ3 was protective against dementia, neurofibrillary tangles, and CAA. Very few other factors were predictive of pathology. Conclusions: Differences between predictors for dementia in younger old versus oldest old populations, as well as for dementia versus pathology, should be considered more carefully in future studies.

Original languageEnglish
Article number11
Pages (from-to)11
JournalAlzheimer's Research and Therapy
Volume11
Issue number1
DOIs
Publication statusPublished - 22 Jan 2019
MoE publication typeA1 Journal article-refereed

Fingerprint

Neurosciences
Dementia
Cohort Studies
Health
Pathology
Amyloid
Alzheimer Disease
Cerebral Amyloid Angiopathy
Neurofibrillary Tangles
Area Under Curve
Neuropathology
Life Style
Synucleins
Genotype
Amyloid Plaques
Sclerosis
Cognition
Population
Autopsy
Alleles

Keywords

  • Dementia
  • Neuropathology
  • Oldest old
  • Prediction
  • Supervised machine learning

Cite this

Hall, Anette ; Pekkala, Timo ; Polvikoski, Tuomo ; van Gils, Mark ; Kivipelto, Miia ; Lötjönen, Jyrki ; Mattila, Jussi ; Kero, Mia ; Myllykangas, Liisa ; Mäkelä, Mira ; Oinas, Minna ; Paetau, Anders ; Soininen, Hilkka ; Tanskanen, Maarit ; Solomon, Alina. / Prediction models for dementia and neuropathology in the oldest old : The Vantaa 85+ cohort study 11 Medical and Health Sciences 1109 Neurosciences. In: Alzheimer's Research and Therapy. 2019 ; Vol. 11, No. 1. pp. 11.
@article{445be468047c4aac971455a27c5f69e0,
title = "Prediction models for dementia and neuropathology in the oldest old: The Vantaa 85+ cohort study 11 Medical and Health Sciences 1109 Neurosciences",
abstract = "Background: We developed multifactorial models for predicting incident dementia and brain pathology in the oldest old using the Vantaa 85+ cohort. Methods: We included participants without dementia at baseline and at least 2 years of follow-up (N = 245) for dementia prediction or with autopsy data (N = 163) for pathology. A supervised machine learning method was used for model development, considering sociodemographic, cognitive, clinical, vascular, and lifestyle factors, as well as APOE genotype. Neuropathological assessments included β-amyloid, neurofibrillary tangles and neuritic plaques, cerebral amyloid angiopathy (CAA), macro- and microscopic infarcts, α-synuclein pathology, hippocampal sclerosis, and TDP-43. Results: Prediction model performance was evaluated using AUC for 10 × 10-fold cross-validation. Overall AUCs were 0.73 for dementia, 0.64-0.68 for Alzheimer's disease (AD)- or amyloid-related pathologies, 0.72 for macroinfarcts, and 0.61 for microinfarcts. Predictors for dementia were different from those in previous reports of younger populations; for example, age, sex, and vascular and lifestyle factors were not predictive. Predictors for dementia versus pathology were also different, because cognition and education predicted dementia but not AD- or amyloid-related pathologies. APOE genotype was most consistently present across all models. APOE alleles had a different impact: ϵ4 did not predict dementia, but it did predict all AD- or amyloid-related pathologies; ϵ2 predicted dementia, but it was protective against amyloid and neuropathological AD; and ϵ3ϵ3 was protective against dementia, neurofibrillary tangles, and CAA. Very few other factors were predictive of pathology. Conclusions: Differences between predictors for dementia in younger old versus oldest old populations, as well as for dementia versus pathology, should be considered more carefully in future studies.",
keywords = "Dementia, Neuropathology, Oldest old, Prediction, Supervised machine learning",
author = "Anette Hall and Timo Pekkala and Tuomo Polvikoski and {van Gils}, Mark and Miia Kivipelto and Jyrki L{\"o}tj{\"o}nen and Jussi Mattila and Mia Kero and Liisa Myllykangas and Mira M{\"a}kel{\"a} and Minna Oinas and Anders Paetau and Hilkka Soininen and Maarit Tanskanen and Alina Solomon",
year = "2019",
month = "1",
day = "22",
doi = "10.1186/s13195-018-0450-3",
language = "English",
volume = "11",
pages = "11",
journal = "Alzheimer's Research and Therapy",
issn = "1758-9193",
number = "1",

}

Hall, A, Pekkala, T, Polvikoski, T, van Gils, M, Kivipelto, M, Lötjönen, J, Mattila, J, Kero, M, Myllykangas, L, Mäkelä, M, Oinas, M, Paetau, A, Soininen, H, Tanskanen, M & Solomon, A 2019, 'Prediction models for dementia and neuropathology in the oldest old: The Vantaa 85+ cohort study 11 Medical and Health Sciences 1109 Neurosciences', Alzheimer's Research and Therapy, vol. 11, no. 1, 11, pp. 11. https://doi.org/10.1186/s13195-018-0450-3

Prediction models for dementia and neuropathology in the oldest old : The Vantaa 85+ cohort study 11 Medical and Health Sciences 1109 Neurosciences. / Hall, Anette; Pekkala, Timo; Polvikoski, Tuomo; van Gils, Mark; Kivipelto, Miia; Lötjönen, Jyrki; Mattila, Jussi; Kero, Mia; Myllykangas, Liisa; Mäkelä, Mira; Oinas, Minna; Paetau, Anders; Soininen, Hilkka; Tanskanen, Maarit; Solomon, Alina (Corresponding Author).

In: Alzheimer's Research and Therapy, Vol. 11, No. 1, 11, 22.01.2019, p. 11.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Prediction models for dementia and neuropathology in the oldest old

T2 - The Vantaa 85+ cohort study 11 Medical and Health Sciences 1109 Neurosciences

AU - Hall, Anette

AU - Pekkala, Timo

AU - Polvikoski, Tuomo

AU - van Gils, Mark

AU - Kivipelto, Miia

AU - Lötjönen, Jyrki

AU - Mattila, Jussi

AU - Kero, Mia

AU - Myllykangas, Liisa

AU - Mäkelä, Mira

AU - Oinas, Minna

AU - Paetau, Anders

AU - Soininen, Hilkka

AU - Tanskanen, Maarit

AU - Solomon, Alina

PY - 2019/1/22

Y1 - 2019/1/22

N2 - Background: We developed multifactorial models for predicting incident dementia and brain pathology in the oldest old using the Vantaa 85+ cohort. Methods: We included participants without dementia at baseline and at least 2 years of follow-up (N = 245) for dementia prediction or with autopsy data (N = 163) for pathology. A supervised machine learning method was used for model development, considering sociodemographic, cognitive, clinical, vascular, and lifestyle factors, as well as APOE genotype. Neuropathological assessments included β-amyloid, neurofibrillary tangles and neuritic plaques, cerebral amyloid angiopathy (CAA), macro- and microscopic infarcts, α-synuclein pathology, hippocampal sclerosis, and TDP-43. Results: Prediction model performance was evaluated using AUC for 10 × 10-fold cross-validation. Overall AUCs were 0.73 for dementia, 0.64-0.68 for Alzheimer's disease (AD)- or amyloid-related pathologies, 0.72 for macroinfarcts, and 0.61 for microinfarcts. Predictors for dementia were different from those in previous reports of younger populations; for example, age, sex, and vascular and lifestyle factors were not predictive. Predictors for dementia versus pathology were also different, because cognition and education predicted dementia but not AD- or amyloid-related pathologies. APOE genotype was most consistently present across all models. APOE alleles had a different impact: ϵ4 did not predict dementia, but it did predict all AD- or amyloid-related pathologies; ϵ2 predicted dementia, but it was protective against amyloid and neuropathological AD; and ϵ3ϵ3 was protective against dementia, neurofibrillary tangles, and CAA. Very few other factors were predictive of pathology. Conclusions: Differences between predictors for dementia in younger old versus oldest old populations, as well as for dementia versus pathology, should be considered more carefully in future studies.

AB - Background: We developed multifactorial models for predicting incident dementia and brain pathology in the oldest old using the Vantaa 85+ cohort. Methods: We included participants without dementia at baseline and at least 2 years of follow-up (N = 245) for dementia prediction or with autopsy data (N = 163) for pathology. A supervised machine learning method was used for model development, considering sociodemographic, cognitive, clinical, vascular, and lifestyle factors, as well as APOE genotype. Neuropathological assessments included β-amyloid, neurofibrillary tangles and neuritic plaques, cerebral amyloid angiopathy (CAA), macro- and microscopic infarcts, α-synuclein pathology, hippocampal sclerosis, and TDP-43. Results: Prediction model performance was evaluated using AUC for 10 × 10-fold cross-validation. Overall AUCs were 0.73 for dementia, 0.64-0.68 for Alzheimer's disease (AD)- or amyloid-related pathologies, 0.72 for macroinfarcts, and 0.61 for microinfarcts. Predictors for dementia were different from those in previous reports of younger populations; for example, age, sex, and vascular and lifestyle factors were not predictive. Predictors for dementia versus pathology were also different, because cognition and education predicted dementia but not AD- or amyloid-related pathologies. APOE genotype was most consistently present across all models. APOE alleles had a different impact: ϵ4 did not predict dementia, but it did predict all AD- or amyloid-related pathologies; ϵ2 predicted dementia, but it was protective against amyloid and neuropathological AD; and ϵ3ϵ3 was protective against dementia, neurofibrillary tangles, and CAA. Very few other factors were predictive of pathology. Conclusions: Differences between predictors for dementia in younger old versus oldest old populations, as well as for dementia versus pathology, should be considered more carefully in future studies.

KW - Dementia

KW - Neuropathology

KW - Oldest old

KW - Prediction

KW - Supervised machine learning

UR - http://www.scopus.com/inward/record.url?scp=85060370934&partnerID=8YFLogxK

U2 - 10.1186/s13195-018-0450-3

DO - 10.1186/s13195-018-0450-3

M3 - Article

C2 - 30670070

AN - SCOPUS:85060370934

VL - 11

SP - 11

JO - Alzheimer's Research and Therapy

JF - Alzheimer's Research and Therapy

SN - 1758-9193

IS - 1

M1 - 11

ER -